Tag: prompting
All the articles with the tag "prompting".
-
Six New Context Engineering Rules for Claude 5, and the 1,473 Lines I Cut
After reading Anthropic's context engineering guidance for Claude 5, I turned the key points into nine cards, then cut 1,473 lines from a harness I had built up over four model generations.
-
Porting Old Prompts to Opus 5: A Nine-Card Migration Guide
Nine cards I made after reading Anthropic's official Opus 5 prompting guide: response length, agent narration, task boundaries, subagent delegation, self-correction, and what happens when you turn thinking off.
-
Claude 5 時代的情境工程六條新規則，與我砍掉的 1473 行 harness
讀完 Anthropic 對 Claude 5 的情境工程指南後，我把重點做成九張圖卡，然後照著把累積四個世代的 harness 削掉 1473 行。
-
舊 prompt 搬到 Opus 5：九張卡的遷移指南
讀完 Anthropic 官方的 Opus 5 提示指南後整理的九張卡：回答長度、代理敘述、任務邊界、子代理委派、自我修正，還有關掉 thinking 的副作用。
-
GPT-image-2 Wants Fewer Constraints — Plus a Consistency Drill
The "ugly crayon doodle" prompt that went viral overseas works because over-constraint kills GPT-image-2's creativity. Here is what I observed this week — including why routing prompts through Claude makes things worse, and why "consistency" matters more than raw image quality at work.
-
GPT-image-2 越少約束越好，加上一個一致性練習
國外最近流行的「笨拙塗鴉風」prompt，越約束越糟，越放任越驚喜。這篇整理我這週對 GPT-image-2 的觀察：包括為什麼透過 Claude 轉交反而會壞事、以及在 Canva 場景下「保持一致性」這件事比生圖能力更值錢。